Use of machine learning algorithm for the better prediction of SR peculiarities of WEDM of Nimonic-90 superalloy

• Autorzy: Singh Nain S. , Sai R. , Sihag P. , Vambol S. , Vambol V.

Identyfikatory

DOI

10.5604/01.3001.0013.1422

• Języki publikacji: EN

Abstrakty

EN

Purpose: With the end goal to fulfil stringent structural shape of the component in aeronautics industry, machining of Nimonic-90 super alloy turns out to be exceptionally troublesome and costly by customary procedures, for example, milling, grinding, turning, etc. For that reason, the manufacture and design engineer worked on contactless machining process like EDM and WEDM. Based on previous studies, it has been observed that rare research work has been published pertaining to the use of machine learning in manufacturing. Therefore the current research work proposed the use of SVM, GP and ANN methods to evaluate the WEDM of Nimonic-90. Design/methodology/approach: The experiments have been performed on the WEDM considering five process variables. The Taguchi L 18 mixed type array is used to formulate the experimental plan. The surface roughness is checked by using surface contact profilometre. The evolutionary algorithms like SVM, GP and ANN approaches have been used to evaluate the SR of WEDM of Nimonic-90 super alloy. Findings: The entire models present the significant results for the better prediction of SR peculiarities of WEDM of Nimonic-90 superalloy. The GP PUK kernel model is dominating the entire model. Research limitations/implications: The investigation was carried for the Nimonic-90 super alloy is selected as a work material. Practical implications: The results of this study provide an opportunity to conduct contactless processing superalloy Nimonic-90. At the same time, this contactless process is much cheaper, faster and more accurate. Originality/value: An experimental work has been reported on the WEDM of Udimet-L605 and use of advance machine learning algorithm and optimization approaches like SVM, and GRA is recommended. A study on WEDM of Inconel 625 has been explored and optimized the process using Taguchi coupled with grey relational approach. The applicability of some evolutionary algorithm like random forest, M5P, and SVM also tested to evaluate the WEDM of Udimet-L605.The fuzzy- inference and BP-ANN approached is used to evaluate the WEDM process. The multi-objective optimization using ratio analysis approach has been utilized to evaluate the WEDM of high carbon & chromium steel. But this current research work proposed the use of SVM, GP and ANN methods to evaluate the WEDM of Nimonic-90.

Słowa kluczowe

EN

support vector machine; Gaussian process; artificial neural network; WEDM

PL

maszyna wektorów nośnych; proces gaussowski; sztuczna sieć neuronowa; WEDM

• Wydawca: International OCSCO World Press
• Czasopismo: Archives of Materials Science and Engineering
• Rocznik: 2019
• Tom: Vol. 95, nr 1
• Strony: 12--19
• Opis fizyczny: Bibliogr. 24 poz.

Twórcy

autor

Singh Nain S.

• Centre for Materials and Manufacturing, Department of Mechanical Engineering, CMR College of Engineering & Technology, Kandlakoya, Hyderabad-501401, Telangana, India

autor

Sai R.

• Department of Automobile Engineering, Government Polytechnic College Ambala, India

autor

Sihag P.

• Department of Civil Engineering, National Institute of Technology Kurukshetra, India

autor

Vambol S.

• Department of Applied Mechanics and Technologies of Environmental Protection, National University of Civil Defence of Ukraine, 61023, Chernyshevska str., 94, Kharkiv, Ukraine

autor

Vambol V.

• Department of logistics and Technical Support of Rescue Operations, National University of Civil Defence of Ukraine, 61023, Chernyshevska str., 94, Kharkiv, Ukraine

Bibliografia

• [1] P. Maruschak, S. Panin, I. Danyliuk, L. Poberezhnyi, T. Pyrig, R. Bishchak, I. Vlasov, Structural and mechanical defects of materials of offshore and onshore main gas pipelines after long-term operation, Open Engineering 5/1 (2015) 365-372.
• [2] L.Y. Poberezhnyi, P.O. Marushchak, A.P. Sorochak, D. Draganovska, A. V. Hrytsanchuk, B. V. Mishchuk, Corrosive and Mechanical Degradation of Pipelines in Acid Soils, Strength of Materials 49/4 (2017) 539-549.
• [3] V. Vambol Numerical integration of the process of cooling gas formed by thermal recycling of waste, Eastem-European Journal of Enterprise Technologies 6/8(84) (2016) 48-53, DOI: 10.15587/1729-4061. 2016.85455.
• [4] V. Bezsonnyi, O. Tretyakov, B. Khalmuradov, R. Ponomarenko, Examining the dynamics and modeling of oxygen regime of chervonooskil water reservoir, Eastern-European Journal of Enterprise Technologies 5/10(89) (2017) 32-38, DOI: 10.15587/1729-4061. 2017.109477.
• [5] M.I. Jordan, T.M. Mitchell, Machine learning: Trends, perspectives, and prospects, Science 349/6245 (2015) 255-260, DOI: 10.1126/science.aaa8415.
• [6] D. Sokolov, V. Sobyna, S. Vambol, V. Vambol, Substantiation of the choice of the cutter material and method of its hardening, working under the action of friction and cyclic loading, Archives of Materials Science and Engineering 94/2 (2018) 49-54, DOI: 10.5604/01.3001.0012.8658.
• [7] P.O. Maruschak, I.B. Okipnyi, L.Y. Poberezhnyi, E.V. Maruschak, Study of heat-resistant steel strain hardening by indentation, Metallurgist 56/11-12 (2013) 946-951.
• [8] M. Kumar, H. Singh, Multi response optimization in wire electrical discharge machining of Inconel X-750 using Taguchi’s technique and grey relational analysis, Cogent Engineering 3/1 (2016) 1266123, DOI: 10.1080/23311916.2016.1266123.
• [9] S.J. Hwang, Y.H. Tsai, Multi-response optimization of surface roughness roundness and MRR in precision turn-boring of 15-5PH stainless steel using taguchi-grey approach, Preprints (2017) 2017040136, DOI: 10.20944/preprints201704.0136.vl.
• [10] D. Kumar, H.S. Payal, N. Beri, Taguchi-Grey established optimisation for M2-tool steel with conventional/pm electrodes on edm with and without powder mixing dielectric, Pertanika Journal of Science and Technology 25/4 (2017) 1331-1342.
• [11] S.S. Nain, D. Garg, S. Kumar, Prediction of the performance characteristics of WEDM on Udimet- L605 using different modelling techniques, Materials Today: Proceedings 4/2 (2017) 546-556.
• [12] S.S. Nain, D. Garg, S. Kumar, Modeling and optimization of process variables of wire-cut electric discharge machining of super alloy Udimet-L605, Engineering Science and Technology, an International Journal 20/1 (2017) 247-264.
• [13] A.K. Parida, K. Maity, Comparison the machinability of Inconel 718, Inconel 625 and Monel 400 in hot turning operation, Engineering Science and Technology, an International Journal 21/3 (2018) 364-370, DOI: https://doi.Org/10.1016/j.jestch.2018.03.018.
• [14] S. Kumar, S. Dhanabalan, Influence of WEDM parameters on surface roughness and cutting speed for NI- based superalloy and multi-parametric optimization using taguchi and grey relational analysis, International Journal of Ethics in Engineering & Management Education 5/4 (2018) 7-13.
• [15] P.K. Karsh, H. Singh, Multi-characteristic optimization in wire electrical discharge machining of inconel-625 by using taguchi-grey relational analysis (GRA) approach: optimization of an existing component/product for better quality at a lower cost, in: K. Kumar, J.P. Davim (Eds.), Design and Optimization of Mechanical Engineering Products, IGI Global, 2018, 281-303.
• [16] C. Nandakumar, B. Mohan, S. Khan, A. Midthur, Experimental investigation on machinability of Inconel 800 using CNC WEDM and modeling of process parameters, Journal of Advanced Microscopy Research 13/2 (2018) 160-165.
• [17] S.S. Nain, D. Garg, S. Kumar, Performance evaluation of the WEDM process of aeronautics super alloy, Materials and Manufacturing Processes 33/16 (2018) 1793-1808, DOI: 10.1080/10426914.2018.1476761.
• [18] S.S. Nain, D. Garg, S. Kumar, Evaluation and analysis of cutting speed, wire wear ratio, and dimensional deviation of wire electric discharge machining of super alloy Udimet-L605 using support vector machine and grey relational analysis, Advances in Manufacturing 6/2 (2018) 225-246.
• [19] S.S. Nain, D. Garg, S. Kumar, Investigation for obtaining the optimal solution for improving the performance of WEDM of super alloy Udimet-L605 using particle swarm optimization, Engineering Science and Technology, an International Journal 21/2 (2018) 261-273.
• [20] S.S. Nain, P. Sihag, S. Luthra, Performance evaluation of Fuzzy-Logic and BP-ANN methods for WEDM of aeronautics super alloy, MethodsX 5 (2018) 890-908, DOI: https://doi.Org/10.1016/j.mex.2018.04.006.
• [21] A. Angelaki, S.S. Nain, V. Singh, P. Sihag, Estimation of models for cumulative infiltration of soil using machine learning methods, ISH Journal of Hydraulic Engineering (2018) 1-8, DOI: https://doi.org/10.1080/ 09715010.2018.1531274.
• [22] S.K. Sahoo, S.S. Naik, J. Rana, Experimental analysis of wire EDM process parameters for micromachining of high carbon high chromium steel by using MOORA technique, in: K. Kumar, D. Zindani, N. Kumari, J.P. Davim (Eds.), Micro and Nano Machining of Engineering Materials, Springer, 2019, 137-148.
• [23] V.N. Vapnik, The Nature of Statistical Learning Theory, Springer, New York, 1995.
• [24] C.E. Rasmussen, C. K. I. Williams, Gaussian Processes for Machine Learning, The MIT Press Cambridge, MA, 2006.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).